addy-hypr4 commited on
Commit
527332b
·
1 Parent(s): 8f99f92

updated translit model and changed qwen asr to finetuned verisonv

Browse files
.gitattributes CHANGED
@@ -47,3 +47,5 @@ tts/kokoro/model.onnx filter=lfs diff=lfs merge=lfs -text
47
  tts/kokoro/*.bin filter=lfs diff=lfs merge=lfs -text
48
  tts/kokoro/*.tar.gz filter=lfs diff=lfs merge=lfs -text
49
  *.gguf filter=lfs diff=lfs merge=lfs -text
 
 
 
47
  tts/kokoro/*.bin filter=lfs diff=lfs merge=lfs -text
48
  tts/kokoro/*.tar.gz filter=lfs diff=lfs merge=lfs -text
49
  *.gguf filter=lfs diff=lfs merge=lfs -text
50
+ stt filter=lfs diff=lfs merge=lfs -text
51
+ translit filter=lfs diff=lfs merge=lfs -text
manifest.json CHANGED
@@ -12,50 +12,50 @@
12
  {
13
  "id": "translit_encoder",
14
  "path": "translit/encoder.onnx",
15
- "size": 9511984,
16
- "sha256": "b439795a8387059c76e471f5d7ef536439cae1958442d7db52f46676b99e7ddc",
17
  "required": true
18
  },
19
  {
20
  "id": "translit_decoder",
21
  "path": "translit/decoder.onnx",
22
- "size": 6690514,
23
- "sha256": "23b32436e3aaf395c1fe677bdb7d5b52322362941310de51a77ca19140846caa",
24
  "required": true
25
  },
26
  {
27
  "id": "translit_input_vocab",
28
  "path": "translit/input_vocab.json",
29
- "size": 946,
30
- "sha256": "f530055fe3d5c5fffe590bafa49a18c59cfa36502406a319a92948d56d447c2f",
31
  "required": true
32
  },
33
  {
34
  "id": "translit_target_vocab",
35
  "path": "translit/target_vocab.json",
36
- "size": 346,
37
- "sha256": "81a34f107f4e7f95fb9d0866e6ab4ad85de6f1e4a58935d611e921889744fa5d",
38
  "required": true
39
  },
40
  {
41
  "id": "stt_conv_frontend",
42
  "path": "stt/qwen3-asr/conv_frontend.onnx",
43
  "size": 44148281,
44
- "sha256": "d22dc4423e0940e49884e903d2ea2f7e5567c14fc1aed97e4e26d6b8f208ef9e",
45
  "required": true
46
  },
47
  {
48
  "id": "stt_encoder",
49
  "path": "stt/qwen3-asr/encoder.int8.onnx",
50
  "size": 182491662,
51
- "sha256": "60748d3e6744a57c9c91e1b17424a6c2990567e8adceb0783940c03ed98fa9d9",
52
  "required": true
53
  },
54
  {
55
  "id": "stt_decoder",
56
  "path": "stt/qwen3-asr/decoder.int8.onnx",
57
- "size": 755914231,
58
- "sha256": "4f6885be5959ae26af3089d38ee7972c5fafbeeb1cf8d5e76eab6d8b61ca5771",
59
  "required": true
60
  },
61
  {
 
12
  {
13
  "id": "translit_encoder",
14
  "path": "translit/encoder.onnx",
15
+ "size": 9529392,
16
+ "sha256": "af1ed31d5af319a353587c746b5c7540646e154d977d7614081c30f8bfb40564",
17
  "required": true
18
  },
19
  {
20
  "id": "translit_decoder",
21
  "path": "translit/decoder.onnx",
22
+ "size": 6819685,
23
+ "sha256": "4930f3460baf4c0f75a346e1320579469b4ff5e00d3e62375cbcb0cee5120aa3",
24
  "required": true
25
  },
26
  {
27
  "id": "translit_input_vocab",
28
  "path": "translit/input_vocab.json",
29
+ "size": 1395,
30
+ "sha256": "b7126832254c449c9a208ec650feae5682a7f77323fd2e9bf2ad29c1ab7332e2",
31
  "required": true
32
  },
33
  {
34
  "id": "translit_target_vocab",
35
  "path": "translit/target_vocab.json",
36
+ "size": 787,
37
+ "sha256": "bd5e364110187e05fcbf00529af0facf45a7838e2aa6b410390af1d80ff08f96",
38
  "required": true
39
  },
40
  {
41
  "id": "stt_conv_frontend",
42
  "path": "stt/qwen3-asr/conv_frontend.onnx",
43
  "size": 44148281,
44
+ "sha256": "1f38b879b0871c9f689b092ad4fa85c68ef473c585dcf53d50a029fe8a0ab0cb",
45
  "required": true
46
  },
47
  {
48
  "id": "stt_encoder",
49
  "path": "stt/qwen3-asr/encoder.int8.onnx",
50
  "size": 182491662,
51
+ "sha256": "ae0cf814d9cd5249b98a1aa9199511d0c0a0c5c8b3059532637fa3cb4785c60c",
52
  "required": true
53
  },
54
  {
55
  "id": "stt_decoder",
56
  "path": "stt/qwen3-asr/decoder.int8.onnx",
57
+ "size": 755914121,
58
+ "sha256": "9604e5f8c06c90c167ecfa63368783b8622125771b11ec595a3e1dcbcf239dd5",
59
  "required": true
60
  },
61
  {
stt/qwen3-asr/conv_frontend.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d22dc4423e0940e49884e903d2ea2f7e5567c14fc1aed97e4e26d6b8f208ef9e
3
  size 44148281
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f38b879b0871c9f689b092ad4fa85c68ef473c585dcf53d50a029fe8a0ab0cb
3
  size 44148281
stt/qwen3-asr/decoder.int8.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f6885be5959ae26af3089d38ee7972c5fafbeeb1cf8d5e76eab6d8b61ca5771
3
- size 755914231
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9604e5f8c06c90c167ecfa63368783b8622125771b11ec595a3e1dcbcf239dd5
3
+ size 755914121
stt/qwen3-asr/encoder.int8.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60748d3e6744a57c9c91e1b17424a6c2990567e8adceb0783940c03ed98fa9d9
3
  size 182491662
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0cf814d9cd5249b98a1aa9199511d0c0a0c5c8b3059532637fa3cb4785c60c
3
  size 182491662
translit/decoder.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23b32436e3aaf395c1fe677bdb7d5b52322362941310de51a77ca19140846caa
3
- size 6690514
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4930f3460baf4c0f75a346e1320579469b4ff5e00d3e62375cbcb0cee5120aa3
3
+ size 6819685
translit/encoder.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b439795a8387059c76e471f5d7ef536439cae1958442d7db52f46676b99e7ddc
3
- size 9511984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af1ed31d5af319a353587c746b5c7540646e154d977d7614081c30f8bfb40564
3
+ size 9529392
translit/input_vocab.json CHANGED
@@ -3,73 +3,107 @@
3
  "<unk>": 1,
4
  "<s>": 2,
5
  "</s>": 3,
6
- "": 4,
7
- "": 5,
8
- "": 6,
9
- "": 7,
10
- "": 8,
11
- "": 9,
12
- "": 10,
13
- "": 11,
14
  "ं": 12,
15
- "": 13,
16
- "": 14,
17
- "": 15,
18
- "": 16,
19
- "ि": 17,
20
- "": 18,
21
- "": 19,
22
- "": 20,
23
- "": 21,
24
- "": 22,
25
  "ी": 23,
26
- "": 24,
27
- "": 25,
28
- "": 26,
29
- "": 27,
30
- "": 28,
31
- "": 29,
32
- "": 30,
33
- "": 31,
34
- "": 32,
35
- "": 33,
36
- "": 34,
37
- "": 35,
38
- "": 36,
39
- "": 37,
40
- "": 38,
41
- "": 39,
42
- "": 40,
43
- "": 41,
44
- "": 42,
45
- "": 43,
46
- "": 44,
47
- "": 45,
48
- "": 46,
49
- "": 47,
50
- "": 48,
51
- "": 49,
52
- "": 50,
53
- "": 51,
54
- "": 52,
55
- "": 53,
56
- "": 54,
57
- "": 55,
58
- "": 56,
59
- "": 57,
60
- "": 58,
61
- "": 59,
62
- "": 60,
63
- "": 61,
64
- "": 62,
65
- "": 63,
66
- "": 64,
67
- "": 65,
68
  "ॅ": 66,
69
- "": 67,
70
- "": 68,
71
- "": 69,
72
- "": 70,
73
- "": 71,
74
- "": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  }
 
3
  "<unk>": 1,
4
  "<s>": 2,
5
  "</s>": 3,
6
+ "": 4,
7
+ "": 5,
8
+ "": 6,
9
+ "ि": 7,
10
+ "": 8,
11
+ "": 9,
12
+ "": 10,
13
+ "": 11,
14
  "ं": 12,
15
+ "": 13,
16
+ "": 14,
17
+ "": 15,
18
+ "": 16,
19
+ "": 17,
20
+ "": 18,
21
+ "": 19,
22
+ "": 20,
23
+ "": 21,
24
+ "": 22,
25
  "ी": 23,
26
+ "": 24,
27
+ "": 25,
28
+ "": 26,
29
+ "": 27,
30
+ "": 28,
31
+ "": 29,
32
+ "": 30,
33
+ "": 31,
34
+ "": 32,
35
+ "": 33,
36
+ "": 34,
37
+ "": 35,
38
+ "": 36,
39
+ "": 37,
40
+ "": 38,
41
+ "": 39,
42
+ "": 40,
43
+ "": 41,
44
+ "": 42,
45
+ "": 43,
46
+ "": 44,
47
+ "": 45,
48
+ "": 46,
49
+ "": 47,
50
+ "": 48,
51
+ "": 49,
52
+ "": 50,
53
+ "": 51,
54
+ "": 52,
55
+ "": 53,
56
+ "": 54,
57
+ "": 55,
58
+ "": 56,
59
+ "": 57,
60
+ "": 58,
61
+ "": 59,
62
+ "": 60,
63
+ "": 61,
64
+ "": 62,
65
+ "": 63,
66
+ "": 64,
67
+ "": 65,
68
  "ॅ": 66,
69
+ "": 67,
70
+ "": 68,
71
+ "": 69,
72
+ "": 70,
73
+ "": 71,
74
+ "": 72,
75
+ "ड़": 73,
76
+ "४": 74,
77
+ "॰": 75,
78
+ "ढ़": 76,
79
+ "फ़": 77,
80
+ "ॐ": 78,
81
+ "३": 79,
82
+ "२": 80,
83
+ "क़": 81,
84
+ "०": 82,
85
+ "ऍ": 83,
86
+ "ॄ": 84,
87
+ "१": 85,
88
+ "ख़": 86,
89
+ "॥": 87,
90
+ "ॆ": 88,
91
+ "ग़": 89,
92
+ "९": 90,
93
+ "७": 91,
94
+ "ऒ": 92,
95
+ "॔": 93,
96
+ "॒": 94,
97
+ "ऎ": 95,
98
+ "ऽ": 96,
99
+ "ऩ": 97,
100
+ "ॠ": 98,
101
+ "॑": 99,
102
+ "ऱ": 100,
103
+ "ऴ": 101,
104
+ "ॣ": 102,
105
+ "ऌ": 103,
106
+ "ॡ": 104,
107
+ "य़": 105,
108
+ "॓": 106
109
  }
translit/target_vocab.json CHANGED
@@ -3,31 +3,67 @@
3
  "<unk>": 1,
4
  "<s>": 2,
5
  "</s>": 3,
6
- "v": 4,
7
  "a": 5,
8
- "k": 6,
9
- "t": 7,
10
- "l": 8,
11
- "c": 9,
12
- "h": 10,
13
- "o": 11,
14
- "n": 12,
15
- "s": 13,
16
- "m": 14,
17
- "b": 15,
18
- "r": 16,
19
- "d": 17,
20
- "i": 18,
21
- "u": 19,
22
- "y": 20,
23
- "j": 21,
24
- "e": 22,
25
- "z": 23,
26
- "g": 24,
27
- "p": 25,
28
- "f": 26,
29
- "x": 27,
30
- "w": 28,
31
  "q": 29,
32
- " ": 30
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
 
3
  "<unk>": 1,
4
  "<s>": 2,
5
  "</s>": 3,
6
+ "g": 4,
7
  "a": 5,
8
+ "n": 6,
9
+ "p": 7,
10
+ "i": 8,
11
+ "t": 9,
12
+ "d": 10,
13
+ "u": 11,
14
+ "r": 12,
15
+ "l": 13,
16
+ "o": 14,
17
+ "h": 15,
18
+ "w": 16,
19
+ "b": 17,
20
+ "y": 18,
21
+ "m": 19,
22
+ "e": 20,
23
+ "s": 21,
24
+ "k": 22,
25
+ "c": 23,
26
+ "v": 24,
27
+ "j": 25,
28
+ "x": 26,
29
+ "z": 27,
30
+ "f": 28,
31
  "q": 29,
32
+ "è": 30,
33
+ "ч": 31,
34
+ "â": 32,
35
+ "ň": 33,
36
+ "é": 34,
37
+ "и": 35,
38
+ "ř": 36,
39
+ "ऐ": 37,
40
+ "ŕ": 38,
41
+ "ť": 39,
42
+ "ż": 40,
43
+ "ü": 41,
44
+ "ő": 42,
45
+ "ĺ": 43,
46
+ "ş": 44,
47
+ "ɓ": 45,
48
+ "ö": 46,
49
+ "ä": 47,
50
+ "ð": 48,
51
+ " ": 49,
52
+ "τ": 50,
53
+ "ú": 51,
54
+ "ж": 52,
55
+ "β": 53,
56
+ "ž": 54,
57
+ "û": 55,
58
+ "с": 56,
59
+ "т": 57,
60
+ "ड": 58,
61
+ "म": 59,
62
+ "प": 60,
63
+ "स": 61,
64
+ "क": 62,
65
+ "ब": 63,
66
+ "ल": 64,
67
+ "ट": 65,
68
+ "à": 66
69
  }